Benjamin Admin
24fdde89c6
v1.1: interview questions are GENERATED from the existing (Master) Controls, not hand-written. Three building blocks: Control->question_intent (corpus/Execution), ~30-40 Master Question Templates (Reasoning), Transition-Prioritization (certs decide which generated questions can be skipped; 217->19 funnel, reuses Company 2A + cert map). v1.2: knowledge production. LLMs produce the first expert DRAFT (the prioritization per transition); BreakPilot reviews + versions + OWNS the canonical library (in Git, not the AI; model-independent, MDQ-00127 v4). Offline multi-model workflow, NOT runtime (deterministic-first: LLM offline-propose, never online-mutate). Hard boundary: the library is an expert DRAFT, not a normative/legal proof -- "cert probably covers X" is Welt-1 (ClaimCoverage), never "erfuellt" (anti-fake-evidence). Reframes the 100 seed questions as validation/template-extraction set. Spec only, no code; non-runtime docs -> no deploy (ADR-001). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
docs-src
MkDocs-based internal documentation site — system architecture, data models, runbooks, API references.
Port: 8011 (container: bp-compliance-docs)
Stack: MkDocs + Material theme, served via nginx.
Build + serve locally
cd docs-src
pip install -r requirements.txt
mkdocs serve # http://localhost:8000
mkdocs build # static output to site/
Known debt (Phase 4)
index.mdis 9436 lines — will be split into per-topic pages with proper mkdocs nav. Target: no single markdown file >500 lines except explicit reference tables.